Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    firstname
    -0.07
    /task
    -0.07
    fun
    -0.07
    pagination
    -0.07
     PART
    -0.07
    骢
    -0.07
     Pon
    -0.07
     worn
    -0.07
     chimney
    -0.07
    _CONDITION
    -0.07
    POSITIVE LOGITS
    扎根
    0.07
    퀄
    0.07
    道理
    0.07
    SH
    0.07
     dropping
    0.07
    ("~/
    0.07
     (>
    0.07
    ㈬
    0.07
    _head
    0.07
     H
    0.06
    Act Density 0.003%

    No Known Activations